IRSPAS 2018
Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/19084
Browse
7 results
Search Results
Item An application of image processing techniques in identifying herbal plants in Sri Lanka(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Azeez, Y. R.; Rajapakse, R. A. C. P.Sri Lanka which is a tropical country situated in South Asian region has a considerable collection of plant species have been utilized by generations as medicinal treatments for a variety of diseases. These diseases ranges from complicated situations such as diabetes, arthritis to cancer and are known to be completely cured using the traditional methods used in Ayurvedic medicines mainly extracted from herbal plants. Dissemination of knowledge regarding herbal plants is restricted mainly to very limited group of people and is passed down from generation to generation who practice traditional medicine. In this study, we therefore attempt to identify herbal plants using machine learning analysis in order to assist more locals to identify them. Among many herbal plants, 5 are chosen to analyze further in detail and the images of the plants will be acquired from social media, Institute of Ayurveda and Alternative medicine website and blogs related to Sri Lankan herbal plants creating a noisy web data set. Several existing algorithms will be analyzed in order to select the suitable algorithms to classify the selected 5 plants accurately and to suggest how they can be used for treatments as recommended by Institute of Ayurveda and Alternative medicine. The main objective of the study is to analyze the noisy image set using deep neural network architectures based on transfer learning, choose the best architecture and create a deep learning model that can be applied effectively for an application. The outcome of this study will be used by locals in identifying herbal plants accurately. The methodology includes gathering data from Institute of Ayurveda and Alternative medicine on plant details and transfer learning based on deep Convolutional Neural Networks used on noisy image set for processing them using tensorflow in a local computer. Images will be retrained on the available neural network architectures such as GoogleNet, Inception v2 and Inception v4 architectures, fine-tuned from pre-trained weights and then the best technique will be selected. The selected algorithm will be fine-tuned using data augmentation techniques on the labeled dataset and hyper-parameter tuning. Conclusively, this study will provide valuable information regarding the herbal plants and possible treatments and help to disseminate knowledge to future generations.Item Identifying paddy diseases with image processing techniques in Sri Lankan context(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Ahamed, M. I. S.; Dimithrie, P. S.; Rajapakse, R. A. C. P.Agriculture is one of the main sectors in Sri Lanka for ages and rice cultivation plays a major role in Sri Lankans' economy. Currently, farmers use traditional methods and they seek the advice of regional agricultural officers to recognize any unknown paddy disease. As a result, the efforts to increase the quality and quantity of rice production are obstructed by paddy diseases especially due to the lack of resources to identify them immediately. Thus, this study attempts to identify paddy diseases using machine learning techniques in relate with Image processing. Among many rice diseases, Rice Blast, Rice Sheath Blight and Bacterial Leaf Blight are focused to analyze further in detail as they are the leading diseases for major destructions in paddy cultivation. Several existing algorithms will be analyzed to select the suitable algorithms for accurate identification of the above three diseases and to suggest better solutions to overcome them as per the recommendations of the Department of Agriculture. Thus, the main object of the study is to analyze different machine learning techniques for the classification in image processing and to get the best technique which can be used effectively for the application. Increasing the disease diagnosing rate and to decreasing the crop destruction rate from these diseases are the main objectives of the study. The outcome of this study will be used by farmers in detecting paddy diseases without depending on others. The methodology includes gathering data from Rice Research and the Development Institute in Bathalagoda (RRDI) and some more images from field visits to the farms. Then MATLAB is to use for preprocessing the datasets to get qualitative images as a data preparation step. For this purpose, we have decided to use the hybrid version of a genetic-algorithm-segmentation based selective principal component analysis method for the feature extraction and develop a featured algorithm from the literature. After the feature extraction, classification will be done by analyzing Support Vector Machine (SVM), KNearest Neighbor (KNN) and Probabilistic neural network (PNN) from the literature and the best technique will be selected. The proposed solutions is to provide precise and scalable visual cues to identify diseases. Conclusively, this study will provide valuable information regarding the reduction of crop destruction from paddy diseases for a better future.Item An expert system for legal counselling in Sri Lanka(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Dissanayake, D. M. L. M.; Rajapakse, R. A. C. P.According to the Human Right Commission of Sri Lanka (HRCSL) publications and their reports, lack of knowledge is the severe problem in Sri Lankan legal system. In addition to this the major reason, lack of resources, lack of awareness raising program on legal matters, lack of confidence of public on presenting their legal problems are some minor reasons. Due to these problems, most of the Sri Lankans face many legal troubles in their day today life. They do not have clear understanding about their legal matters. To reduce these legal problems, they need to have a proper and efficient legal counseling service of an expert legal officer or an expert lawyer. Legal Aid Commission (LAC) is the main legal counselling provider in Sri Lanka. LAC has expert Legal officers to provide these services. However, the commission has limited number of resources. Every counsellor has a huge work load. In addition to the LAC, Institution of human rights and National Child Protection Authority also provide legal counselling. Although there are many legal counselling institutions in Sri Lanka, a decrease of legal problems cannot be observed. Due to these problems, there is an urgent need to develop a legal expert system for the people to get advised for their legal troubles. An expert system is a computer system which is having an ability to reproduction of logical decision-making process of human experts. It consists of a knowledge base and an inference engine. The goal of this study is to develop a software system to assist the preliminary counselling process. It will provide a primary solution to start their solving process of legal problems. This context considers only about the children’s and the women’s rights violations. Extracting the knowledge of the experts in relevant field by observing their counselling process is the first step for achieving this target. Main purpose is to identify the conditions that experts mainly consider when solving legal problems. On the knowledge of legal counselling experts, a rule-based engine has been implemented. For this purpose, information about the selected scenarios are represented by a series of if-then statements. Developing an expert system with a web interface is then carried out. Finally, it is to get the expert users’ feedback to arrive conclusion. Using this system end users can get guidance to their legal problem by selecting one or more answers from a list or by entering data. The developed software system will contribute to increase the legal awareness of the Sri Lankan people by providing a primary solution to their legal matters.Item Blockchain based solution for Sri Lankan agricultural supply chain to ensure food security(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Basnayake, B. M. A. L.; Rajapakse, R. A. C. P.Low quality agricultural products are added to the market daily. Overuse of chemicals in the production process, using uncertified chemicals and mechanisms for preservation and ripening processes, are the major issues with an impact on agricultural product’s quality as well as overall health of the consumers. Mechanisms for identifying the quality of the agricultural products are highly demanded due to the lack of transparency in the current process. A crowd-based decentralized certification system is required instead of a central authority to certify the products. Blockchain technology is emerging as a decentralized and secure infrastructure which can replace involvement of a third party to verify the transactions within the system. The purpose of the research is to implement a blockchain based solution to verify the food quality and the origin of the agricultural supply chain. The data on the transactions, existing certification process, actors and their roles within the Sri Lankan agricultural supply chain context were identified and collected through self-experience and related institutes. The Agricultural department's Good Agricultural Practice certification process was studied to get data on the existing certification process. Furthermore, Hector Kobbakaduwa Agrarian Research and Training Institute’s publications were used to gather data on local food supply chain. All the actors who are engaged with the supply chain must be able to interact with the system to achieve the goal. Each transaction and events related to a product is validated by peers of the blockchain system. Product ownership is changed for each relevant transaction. A token-based mechanism is used to indicate the farmers’ reputation with their products. Farmers can place a certification request regarding their products and, they can be gained reputation tokens for each certification done by peers. A unique Quick Response (QR) code is used to identify each product container or package. In each step of the supply chain, the QR code is used to validate physical product with the virtual product. Consumers will be able to ensure the origin and the quality of each product by scanning the QR Code, with the mobile application. The proposed system will be implemented, following a systematic review of a literature as well as a series of interviews with stakeholders, as a prototype on a private blockchain and validated with the involvement of real users to arrive at conclusions.Item An agent-based simulation study on the impact of emerging motorbikes swarms on the transportation system in Sri Lanka(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Kulathilake, E. R.; Rajapakse, R. A. C. P.Transportation system in Sri Lanka is increasingly getting dependent on private modes rather than public modes. In particular, the motorbike has become the most popular mode of transportation among the middle income category of the society. This increasing trend is well reflected in the rush hour traffic as well as in the growing number of motorbike sales outlets appearing across the country. Our research is based on the question where would this end up if this trend continues. As many East Asian countries such as Vietnam, Indonesia and Thailand are currently suffering from the largely unorganized traffic resulted from motorbike swarms, we see the investigation of the possible impact of this growing tendency to use motorbikes in Sri Lanka on the transportation system as a critical issue that the policy makers should be concerned of. We propose to use computational methods to foresee the future by creating simulation models. For this endeavor, we propose the Agent-Based Modeling and Simulation methodology which is a computational method of studying macro level emerging patterns in a system such as traffic congestion by simulating the micro level interactions of individual entities such as individuals, motor bike riders, pedestrians, other vehicles are modeled as software agents. The primary data to construct the model as well as to calibrate its parameters are collected through a questionnaire distributed among motor bike riders as well as thorough literature review. The data being collected include the background of using motorbike as the primary mode of transportation, the issues in the public transportation system as well as the common driving patterns of individual motorcyclists. Once the model is constructed, the simulation results will be compared with the observations in the real environment to validate the model. The validated model will then be used to make predictions about the future and arrive at conclusions about the future traffic patterns. The implications of this study will be helpful to the policy makers to come up with better strategies to reduce the congestion.Item Investigating the impact of data and analytics strategy in performance of private firms in Sri Lanka(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Wijayasiiriwardane, K. L.; Rajapakse, R. A. C. P.Big Data Analytics (BDA) is considered as a tool to explore new opportunities for an organization to be competitive in dynamic markets. It represents a set of technologies and algorithms to recognize important patterns such as new market opportunities and business propositions as well as to make effective predictions on market behaviors. Therefore, every organization put efforts to use their data, both structured and unstructured, strategically to be competitive. In other words, the performance of modern day firms is expected to have a close tie with the data and analytics strategy being used. However, there are no adequate research studies conducted to systematically evaluate the impact of the data and analytics strategy on the firm performance. In this research we intend to fill this research gap by systematically surveying the elements of the data and analytics strategies of key industry players in Sri Lanka and attempting to identify their relationships with the performance of respective companies. The performance will be evaluate under financial performance, customer retention and reach, growth in sales, growth in profit, return on investment, market performance etc. The research is designed as follows. We first did a comprehensive study on the existing literature about data and analytic strategy and, based on the resource-based theory and dynamic capability view, identified three main dimensions namely Big data analytics management capability, big data analytics talent capability, big data analytics technical capability and eleven sub-dimensions as capabilities to acquire for enhanced performance through data and analytics strategies. This theoretical model is planned to be validated through empirical data. Accordingly, we plan to collect data from managerial level users of a selected group of financial companies who are currently potential beneficiaries of big data capabilities through a questionnaire and subsequent open-ended interviews. The results will be then analyzed with respect to each sub-dimension to derive conclusions about the overall relationship between the data and analytics strategy and firm performance.Item Fintech platform for digitally trusted lending circles based on Ethereum blockchain(Research Symposium on Pure and Applied Sciences, 2018 Faculty of Science, University of Kelaniya, Sri Lanka, 2018) Wijesekara, U. C. K.; Rajapakse, R. A. C. P.This study will focus on the design and development of a software architecture for digitally trusted lending circles on top of blockchain technology to eliminate the currently prevailing problems in the existing physical and digital lending circles. Lending circles are believed by the majority as a healthy and effective mechanism as per the observations of the society and the related literature. Especially, in low to medium income societies, microfinancing techniques and their learnings are rapidly gaining in popularity, although they have the below limitations and pitfalls in its nature. Existing physical and digital Lending circles are formed within a closely associated community. Hence, they are not scalable towards higher pot sizes and cannot be applied to any random set of participants. Thus, they form those circles with those who are a part of the social capital of the leader of a given circle where the opportunity is limited to a set of participants. Apart from that, those lending circles do not have a proper mechanism of authentication and validation of the participants for a given lending circle. Hence, even the current mechanism of digital lending circles prevails a lot of issues. Furthermore, it does not create an opportunity for an arbitrary person to join a given lending circle although he is capable and genuine. Most sustainable solution to the problem would be a software architecture that incorporates a peer-to-peer network (i.e. blockchain) to establish the digital identity and the digital trust element. Furthermore, the new architecture enhances the process of lending circles and mitigate risks by performing critical tasks related to lending circles on the blockchain. The methodology of this research can be described under four major phases. During the first phase, a comprehensive study of literature was done along with the interviewing process to discover the existing limitations and pitfalls in existing software solutions for the lending purpose. The second phase focuses towards designing a novel architecture which can address the prevailing issues of the existing lending circles. A prototype is developed in the third phase to demonstrate the architecture designed under phase 2. Then, the developed prototype is tested with real users. Thus, the final outcomes of this particular study is an innovative software architecture and a proof-of-concept for combining trusted lending and identity management domain on top of blockchain concept along with the other applicable state-of-the-art technologies.